unfreeze — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited unfreeze (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use when you want to widen edit scope. Ending the session does not lift the boundary: it persists in ~/.vibestack/freeze-dir.txt until this runs. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits".
Remove the edit restriction set by /freeze, allowing edits to all directories.
bash "${CLAUDE_SKILL_DIR:-$HOME/.claude/skills/unfreeze}/../freeze/bin/freeze-state.sh" clearThe shared state writer removes the boundary under the same lock /freeze, /guard and /investigate use. This also clears a boundary /investigate acquired and could not release (a killed session). Tell the user the result. On FREEZE_BUSY, retry once the other writer finishes; never delete the state file directly. Note that /freeze hooks remain registered for the session — they will allow all paths since no state file exists. To re-freeze, run /freeze again.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.